R Examples

To determine the FAC code for Y12 from the ORISEWDS_d1 - Master roster file, click on the header for FAC1:

The variable level for each header will be displayed.

Select the FACCODE code set and all associated values will be displayed.

Y12 is Facility Code 6:

Example overview using R for Windows 2.15

After downloading the ORISEWDS_d1 - Master roster file, select everyone that worked at Y12.

Refine the cohort

Select all males at Y12

Determine the vital status for a cohort

After downloading the ORISEWDS_d6 - Master vital status file, show the vital status of all males at Y12
After downloading ORISEWDS_d7 - Death file, select all deceased males who worked at Y12 and their associated cause of death will be displayed.

Determine a cohort who worked in a particular time period

After downloading the ORISEWDS_d2 - Employment data, select all males who were ever hired at Y12 between 1980 and 2000.
Select all Y12 males that were ever employed between 1980 and 2000 and their associated vital status will be displayed.

##Clean the existing environment
remove(list=ls(all=TRUE))

##Set pathing
path <- "C:\\R_Examples\\"

#************************************************************************************
# Example 1 - Selecting Y12 workers
# FAC code 6 is for Y12
# FAC1-Fac10 are checked to determine if they were ever employed at Y12
#************************************************************************************

##Read in ORISEWDS_d1
inputFile <- paste(path, "ORISEWDS_d1.csv", sep="")
dataOriginal <- read.table(nputFile, header=TRUE, sep=",")

##Subset all Y12 workers to get only the males
y12Males <- subset(y12Workers, y12Workers[,"sex"] == "M")

#************************************************************************************
# Example 2 - Selecting vital status for Y12 males
# Import the Master vital status file
#************************************************************************************

##Read in ORISEWDS_d6
inputFile <- paste(path, "ORISEWDS_d6.csv", sep="")
dataVital <- read.table(inputFile, header=TRUE, sep=",")

##Merge the two datasets
y12MalesVital <- merge(y12Males, dataVital, by = "id", all.x = TRUE)

#************************************************************************************
# Example 3 - Selecting deceased males at Y12 and their cause of death
# Import the Death file
#************************************************************************************

##Read in ORISEWDS_d7
inputFile <- paste(path, "ORISEWDS_d7.csv", sep=",")
dataDeath <- read.table(inputFile, header=TRUE, sep=",")

##Merge the two datasets
y12MalesDeath <- merge(y12Males, dataDeath, by="id")

#************************************************************************************
# Example 4 - Employment data for all males who were hired at
# Y12 between 1980 and 2000
# Import the Employment data
#************************************************************************************

##Read in ORISEWDS_d2
inputFile <- paste(path, "ORISEWDS_d2.csv", sep="")
dataEmployment <- read.csv(inputFile, header=TRUE, sep=",")

##Merge the two datasets
y12MalesEmploy <- merge(y12Males, dataEmployment, by="id")

## find rows to remove with hire years outside of range 1980-2000
rowsToRemove <- 0
for(i in 1:length(y12MalesEmploy[,1]))
{
hireDateLength <- nchar(as.character(y12MalesEmploy[i, "hiredate"]))
ifelse(y12MalesEmploy[i, "hiredate"] == "XXXXXXXXXX", yearHire <- 9999,
yearHire <- as.numeric(substr(y12MalesEmploy[i, "hiredate"],
hireDateLength-3, hireDateLength)))

if(yearHire < 1980 | yearHire > 2000)
rowsToRemove <- c(rowsToRemove, i)
}
##Remove rows
y12MalesEmployYears <- y12MalesEmploy[-rowsToRemove,]

#************************************************************************************
# Example 5 - Y12 males ever employed between 1980-2000 and their vital status
#************************************************************************************

##Pull out the unique ID's, maintaining them as a dataframe for the merge
y12MalesEmployUnique <- as.data.frame(unique(y12MalesEmployYears[,"id"]))
colnames(y12MalesEmployUnique) <- "id"

##Merge the two datasets
y12MalesEmployVital <- merge(y12MalesEmployUnique, y12MalesVital, by = "id", all.x = TRUE)

## find rows with NA status and drop them
rowsToRemove <- 0
for(i in 2:length(y12MalesEmployVital[,1]))
{
if(is.na(y12MalesEmployVital[i,"status"]))
rowsToRemove <- c(rowsToRemove, i)
}

##Remove rows
y12MalesEmployVital <- y12MalesEmployVital[-rowsToRemove,]

Next: See Access Examples

Share This Page: